paper-with-me

Papers

Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution

2022-03-15 · Jinsu Yoo, TaeHoon Kim, Sihaeng Lee, Seung Hwan Kim, Honglak Lee, Tae Hyun Kim

Recent transformer-based super-resolution (SR) methods have achieved promising results against conventional CNN-based methods. However, these approaches suffer from essential shortsightedness created by only utilizing the standard self-attention-based reasoning. In this paper, we introduce an effective hybrid SR network to aggregate enriched features, including local features from CNNs and long-range multi-scale dependencies captured by transformers. Specifically, our network comprises transformer and convolutional branches, which synergetically complement each representation during the restoration procedure. Furthermore, we propose a cross-scale token attention module, allowing the transformer branch to exploit the informative relationships among tokens across different scales efficiently. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2203.07682

Code (1)

jinsuyoo/act 공식 구현 pytorch

Tasks

Image RestorationSuper-Resolution

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Image Super-resolution Reconstruction Network based on Enhanced Swin Transformer via Alternating Aggregation of Local-Global Features

2023-12-30 · Yuming Huang, Yingpin Chen, Changhui Wu, Hanrong Xie 외

The Swin Transformer image super-resolution reconstruction network only relies on the long-range relationship of window attention and shifted window attention to explore features. This mechanism has two limitations. On t…

Image Super-ResolutionSuper-Resolution

Dual Aggregation Transformer for Image Super-Resolution

2023-08-07 · ICCV 2023 1 · Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong 외

Transformer has recently gained considerable popularity in low-level vision tasks, including image super-resolution (SR). These networks utilize self-attention along different dimensions, spatial or channel, and achieve …

Image Super-ResolutionSuper-Resolution

HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution

2024-11-27 · Song-Jiang Lai, Tsun-Hin Cheung, Ka-Chun Fung, Kai-wen Xue 외

In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism. However, existing methods often limit self-attention to…

Image Super-ResolutionSuper-Resolution

Learning Enriched Features for Real Image Restoration and Enhancement

2020-03-15 · ECCV 2020 8 · Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat 외

With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing. R…

DenoisingImage DenoisingImage EnhancementImage Restoration+2

Learning Enriched Features for Fast Image Restoration and Enhancement

2022-04-19 · Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat 외

Given a degraded input image, image restoration aims to recover the missing high-quality image content. Numerous applications demand effective image restoration, e.g., computational photography, surveillance, autonomous …

Autonomous VehiclesDeblurringDenoisingImage Denoising+3